• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.4
• /
• pp.129-134
• /
• 2018

Recently, the artificial neural network (ANN) model is a promising technique in the prediction, numerical control, robot control and pattern recognition. We predicted the outside temperature of greenhouse using ANN and utilized the model in greenhouse control. The performance of ANN model was evaluated and compared with multiple regression model(MRM) and support vector machine (SVM) model. The 10-fold cross validation was used as the evaluation method. In order to improve the prediction performance, the data reduction was performed by correlation analysis and new factor were extracted from measured data to improve the reliability of training data. The backpropagation algorithm was used for constructing ANN, multiple regression model was constructed by M5 method. And SVM model was constructed by epsilon-SVM method. As the result showed that the RMSE (Root Mean Squared Error) value of ANN, MRM and SVM were 0.9256, 1.8503 and 7.5521 respectively. In addition, by applying the prediction model to greenhouse heating load calculation, it can increase the income by reducing the energy cost in the greenhouse. The heating load of the experimented greenhouse was 3326.4kcal/h and the fuel consumption was estimated to be 453.8L as the total heating time is $10000^{\circ}C/h$. Therefore, data mining technology of ANN can be applied to various agricultural fields such as precise greenhouse control, cultivation techniques, and harvest prediction, thereby contributing to the development of smart agriculture.

• Journal of Bio-Environment Control
• /
• v.23 no.2
• /
• pp.123-130
• /
• 2014

Oriental melon (Cucumis melo var. makuwa) should be cultivated on the soil and be harvested. It is difficult to find because it is covered with leaves, and furthermore, it is very hard to grip it due to its climbing stems. This study developed and tested oriental melon harvesting robots such as an end-effector, manipulator and identification device. The end effector is divided into a gripper for harvest and a cutter for stems. In addition, it was designed to control the gripping and cutting forces so that the gripper could move four fingers at the same time and the cutter could move back and forth. The manipulator was designed to realize a 4-axis manipulator structure to combine orthogonal coordinate-type and shuttle-type manipulators with L-R type model to rotate based on the central axis. With regard to the identification device, oriental melon was identified using the primary identification global view camera device and secondary identification local view camera device and selected in the prediction of the sugar content or maturity. As a result of the performance test using this device, the average harvest time was 18.2 sec/ea, average pick-up rate was 91.4%, average damage rate was 8.2% and average sorting rate was 72.6%.

• Journal of IKEEE
• /
• v.24 no.2
• /
• pp.654-660
• /
• 2020

Through the output of brain waves during muscle operation, this paper checks whether it is possible to find characteristic vectors of brain waves that are capable of dividing left and right movements by extracting brain waves in specific areas of muscle signal output that include the motion of the left and right muscles or the will of the user within EEG signals, where uncertainties exist considerably. A typical surface EMG and noninvasive brain wave extraction method does not exist to distinguish whether the signal is a motion through the degree of ionization by internal neurotransmitter and the magnitude of electrical conductivity. In the case of joint and motor control through normal robot control systems or electrical signals, signals that can be controlled by the transmission and feedback control of specific signals can be identified. However, the human body lacks evidence to find the exact protocols between the brain and the muscles. Therefore, in this paper, efficiency is verified by utilizing the results of application of CSP (Common Spatial Pattern) filter to verify that the left-hand and right-hand signals can be extracted through brainwave analysis when the subject's behavior is performed. In addition, we propose ways to obtain data through experimental design for verification, to verify the change in results with or without filter application, and to increase the accuracy of the classification.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.2
• /
• pp.123-128
• /
• 2014

This paper presents the study about MGV(Magnetic guidance vehicle) with up-and-down rotating type differential drive unit. Previous MGV needs the landmarks to get the driving information and additional sensor to recognize the landmarks except for localization sensor. Previous MGV requires at least 2 drive units when common fixed differential drive unit is used because it occurs the problems with driving control and localization error from imbalance of the MGV's weight. To solve such problems, we propose the MGV using up-and-down rotating type differential drive unit. Proposed MGV recognizes the driving information from the pattern which is consisted of both pole of magnet without landmarks and additional sensors, and it control the backward movement using up-and-down rotating type differential drive unit instead of common drive units. Proposed MGV considers KF(Kalman filter) to improve the localization accuracy. To verify the performance of proposed method, we designed MGV for the experiment. As the results, we can confirm the performance of propoesed method to recognize the pattern and to control the backward movement. With respect to localization, proposed method has the less RMSE about 5.6904 mm than previous method.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.1
• /
• pp.29-37
• /
• 1999

In general, the information processing capability of a neural network is determined by its architecture and efficient training patterns. However, there is no systematic method for designing neural network and selecting effective training patterns. Evolutionary Algorithms(EAs) are referred to as the methods of population-based optimization. Therefore, EAs are considered as very efficient methods of optimal system design because they can provide much opportunity for obtaining the global optimal solution. In this paper, we propose a new method for finding the optimal structure of neural networks based on competitive co-evolution, which has two different populations. Each population is called the primary population and the secondary population respectively. The former is composed of the architecture of neural network and the latter is composed of training patterns. These two populations co-evolve competitively each other, that is, the training patterns will evolve to become more difficult for learning of neural networks and the architecture of neural networks will evolve to learn this patterns. This method prevents the system from the limitation of the performance by random design of neural networks and inadequate selection of training patterns. In co-evolutionary method, it is difficult to monitor the progress of co-evolution because the fitness of individuals varies dynamically. So, we also introduce the measurement method. The validity and effectiveness of the proposed method are inspected by applying it to the visual servoing of robot manipulators.

• Journal of the Society of Disaster Information
• /
• v.19 no.3
• /
• pp.665-672
• /
• 2023

Purpose: Underground utility tunnel is facility that is jointly house infrastructure such as electricity, water and gas in city, causing condensation problems due to lack of airflow. This paper aims to prevent electricity leakage fires caused by condensation by detecting whether the control panel door in the underground utility tunnel is open using a deep learning model. Method: YOLO, a deep learning object recognition model, is trained to recognize the opening and closing of the control panel door using video data taken by a robot patrolling the underground utility tunnel. To improve the recognition rate, image augmentation is used. Result: Among the image enhancement techniques, we compared the performance of the YOLO model trained using mosaic with that of the YOLO model without mosaic, and found that the mosaic technique performed better. The mAP for all classes were 0.994, which is high evaluation result. Conclusion: It was able to detect the control panel even when there were lights off or other objects in the underground cavity. This allows you to effectively manage the underground utility tunnel and prevent disasters.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.579-584
• /
• 2008

A novel nondestructive testing (NDT) system, which is able to detect a crack with high speed and high spatial resolution, is urgently required for inspecting small cracks on express train wheels. This paper proposes an improved signal processing circuits, which uses the multiple amplifying circuits and the crack indicating pulse output system of the previous scan-type magnetic camera. Hall sensors are arrayed linearly, and the wheel is rotated with static speed in the vertical direction to sensor array direction. Each Hall voltages are amplified, converted and immediately operated by using, amplifying circuits, analog-to-digital converters and $\mu$-processor, respectively. The operated results, ${\partial}V_H/{\partial}t$, are compared with a standard value, which indicates a crack existence. If the ${\partial}V_H/{\partial}t$ is larger than standard value, the pulse signal is output, and indicates the existence of crack. The effectiveness of the novel method was verified by examine using cracks on the wheel specimen model.

• 전자공학회논문지 IE
• /
• v.43 no.4
• /
• pp.65-75
• /
• 2006

This thesis deals with a wavelet-based method of denoising of infrared images contaminated with impulse noise and Gaussian noise, he method of thresholding the wavelet coefficients using derivatives and median absolute deviations of the wavelet coefficients of the detail subbands was proposed to effectively denoise infrared images with noises. Particularly, in order to eliminate the impulse noise the method of generating binary masks indicating locations of the impulse noise was selected. By this method, the threshold values dividing edges and noises were obtained more effectively proving the validity of the denoising method compared with the conventional wavelet shrinkage method.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06a
• /
• pp.227-229
• /
• 2012

한국해양연구원에서 개발하고 있는 해저보행로봇 CR200은 6개의 다리를 이용하여 해저면에서 보행으로 이동하며 정밀 해저탐사 및 작업을 수행할 수 있는 로봇이다. 운용자는 선상제어실에서 유선으로 연결된 CR200을 원격으로 모니터링하거나 제어한다. 특히 안정적인 보행을 위해서는 100Hz의 주기로 CR200의 상태 정보가 선상제어실로 전송되고, 선상제어실에서는 전송된 정보를 기반으로 제어 명령을 산출하여 CR200으로 전송해야 한다. 이러한 주기적인 실시간 제어를 위해서는 일반적으로 실시간 운영체제를 사용하지만, 본 논문에서는 실시간 운영체제를 사용하지 않고 시스템 시간 기반의 백그라운드 프로세스로 동작하는 소프트웨어 타이머를 사용하여 실시간 제어를 하는 방법을 제안하고, 성능 평가 결과를 제시한다. 제안한 방법의 실시간 속성을 검증하기 위하여, 현재 설계에서 운영체제로 고려하고 있는 우분투 10.04와 윈도우즈 7을 CR200에 탑재되는 Advantech 사의 PCM-3362 보드에 설치하여 소프트웨어 타이머의 성능을 10ms부터 100ms까지 각각 실험하였다. 실험결과에 따르면, 두 운영체제에서 모두 누락이 없이 타이머 동작이 수행되었으며, 10ms 간격으로 타이머를 동작하였을 때에 우분투에서는 평균 오차가 $41{\mu}s$이었고 윈도우즈 7에서는 7.7ms였다. 윈도우즈 7에서의 오차는 100Hz 제어 주기에 사용하기에 적합하지 않지만, 우분투에서의 오차는 제어 주기 간격의 0.41%에 불과하기 때문에 해저보행로봇의 실시간 제어에 영향을 주지 않는 오차이다. 따라서 CR200의 임베디드 컴퓨터와 선상제어실의 원격제어 컴퓨터는 우분투 운영체제 상에서 소프트웨어 타이머를 이용하여 상호 연동되도록 구현할 예정이다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1516-1519
• /
• 2004

A tele-operated robot should be used to maintain and inspect nuclear power plants to reduce the radiation exposure to the human operators. During an overhaul of the nuclear power plants in Korea, a ROV(Remotely Operated Vehicle) may enter a cold-leg connected to the reactor to examine the state of the thermal sleeve and it's position in the safety injection nozzle. To measure the positions of the thermal sleeve or scratches from the video images captured during the examination, the camera parameters should be identified. However, the focal length of the CCD camera could be increased to a close up of the target and the aspect ratio and the center of the image could also be varied with capturing devices. So, it is desired to self-calibrated the intrinsic parameters of the camera and capturing device with the video images captured during the examination. In the video image of the safety injection nozzle, two or more circular grooves around the nozzle are shown as ellipse contours. In this paper, we propose a camera self-calibration method using a single image containing two circular grooves which are the greatest circles of the cylindrical nozzle whose radius and distance are known.